Bootstrapping Statistical Processing into a Rule-Based Natural Language Parser

Bootstrapping Statistical Processing into a Rule-based Natural Language Parser Stephen D. Richardson Microsoft Research One Microsoft Way Redmond, WA 98052 Abstract This paper describes a "bootstrapping" method which uses a broad-coverage, rule-based parser to compute probabilities while parsing an untagged corpus of NL text, and which then incorporates those probabilities into the processing of the same parser as it analyzes new text. Results are reported which show that this method can significantly improve the speed and accuracy of the parser without requiring the use of annotated corpora or human-supervised training during the computation of probabilities. 1 Introduction For decades, the majority of NL parsers have been "rule-based." In such parsers, knowledge about the syntactic structure of a language is written in the form of linguistic rules, and these rules are applied by the parser to input text segments in order to produce the resulting parse trees. Information about individual words, such as what parts-of- speech they may be, is usually stored in an online dictionary, or "lexicon," which is accessed by the parser for each word in the input text prior to applying the linguistic rules. Although rule-based parsers are widely-used in real, working NLP systems, they have the disadvantage that extensive amounts of (dictionary) data and labor (to write the rules) by highly-skilled linguists are required in order to create, enhance, and maintain them. This is especially true if the parser is required to have "broad coverage", i.e., if it is to be able to parse NL text from many different domains (what one might call '!general" text). In the last few years, there has been increasing activity in the computational linguistics community focused on making use of statistical methods to acquire information from large corpora of NL text, and on using that information in statistical NL parsers. Instead of being stored in the traditional form of dictionary data and grammatical rules, linguistic knowledge in these parsers is represented as statistical parameters, or probabilities. These probabilities are commonly used together with simpler, less specified, dictionary data and/or rules, thereby taking the place of much of the information created by sldlled labor in rule-based systems. Advantages of the statistical approach that are claimed by its proponents include a significant decrease in the amount of rule coding required to create a parser that performs adequately, and the ability to "tune" a parser to a particular type of text simply by extracting statistical information from the same type of text. Perhaps the most significant disadvantage appears to be the requirement for large amounts of training data, often in the form of large NL text corpora that have been annotated with hand-coded tags specifying parts-of-speech, syntactic function, etc. There have been a number of efforts to extract information from corpora that are not tagged (e.g., Kupiec and Maxwell 1992), but the depth of information thus obtained and its utility in "automatically" creating a NL parser is usually limited. To overcome the need for augmenting corpora with tags in order to obtain more useful …

Content truncated to 500 words